arXiv:2507.13414cs.LGcs.AI2025-07被引 2

在流模型中引入可学习的规范场,提升生成效果。

Gauge Flow Models

  • 在流微分方程中加入可学习的规范场,改进生成过程。
  • 在高斯混合模型上,性能优于同规模或更大传统流模型。
  • 适用于更广泛的生成任务,潜力显著,适合生成模型研究者。

本文提出了一类新型生成流模型——规范流模型(Gauge Flow Models),其在流微分方程中引入了可学习的规范场,并提供了完整的数学框架以描述其构造与性质。通过在高斯混合模型上进行流匹配实验,结果表明,规范流模型在性能上显著优于传统流模型,即使在模型规模相当或更大时亦然。此外,未发表的研究显示,该方法在更广泛的生成任务中也具有提升潜力。

原文摘要 · Abstract (English)

This paper introduces Gauge Flow Models, a novel class of Generative Flow Models. These models incorporate a learnable Gauge Field within the Flow Ordinary Differential Equation (ODE). A comprehensive mathematical framework for these models, detailing their construction and properties, is provided. Experiments using Flow Matching on Gaussian Mixture Models demonstrate that Gauge Flow Models yields significantly better performance than traditional Flow Models of comparable or even larger size. Additionally, unpublished research indicates a potential for enhanced performance across a broader range of generative tasks.

生成模型流模型规范场

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。